Anthropocentric Bias in Language Model Evaluation

Raphaël Millière; Charles Rathkopf

doi:10.1162/coli.a.582

Anthropocentric Bias in Language Model Evaluation

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Evaluating the cognitive capacities of large language models (LLMs) requires overcoming not only anthropomorphic but also anthropocentric biases. This article identifies two types of anthropocentric bias that have been neglected: overlooking how auxiliary factors can impede LLM performance despite competence (auxiliary oversight), and dismissing LLM mechanistic strategies that differ from those of humans as not genuinely competent (mechanistic chauvinism). Mitigating these biases requires an empirical, iterative approach to mapping cognitive tasks to LLM-specific capacities and mechanisms, achieved by supplementing behavioral experiments with mechanistic studies.

Anthology ID:: 2026.cl-1.11
Volume:: Computational Linguistics, Volume 52, Issue 1 - March 2026
Month:: March
Year:: 2026
Address:: Cambridge, MA
Venue:: CL
SIG:
Publisher:: MIT Press
Note:
Pages:: 379–388
Language:
URL:: https://aclanthology.org/2026.cl-1.11/
DOI:: 10.1162/coli.a.582
Bibkey:
Cite (ACL):: Raphaël Millière and Charles Rathkopf. 2026. Anthropocentric Bias in Language Model Evaluation. Computational Linguistics, 52(1):379–388.
Cite (Informal):: Anthropocentric Bias in Language Model Evaluation (Millière & Rathkopf, CL 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.cl-1.11.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@article{milliere-rathkopf-2026-anthropocentric,
    title = "Anthropocentric Bias in Language Model Evaluation",
    author = {Milli{\`e}re, Rapha{\"e}l  and
      Rathkopf, Charles},
    journal = "Computational Linguistics",
    volume = "52",
    number = "1",
    month = mar,
    year = "2026",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://aclanthology.org/2026.cl-1.11/",
    doi = "10.1162/coli.a.582",
    pages = "379--388",
    abstract = "Evaluating the cognitive capacities of large language models (LLMs) requires overcoming not only anthropomorphic but also anthropocentric biases. This article identifies two types of anthropocentric bias that have been neglected: overlooking how auxiliary factors can impede LLM performance despite competence (auxiliary oversight), and dismissing LLM mechanistic strategies that differ from those of humans as not genuinely competent (mechanistic chauvinism). Mitigating these biases requires an empirical, iterative approach to mapping cognitive tasks to LLM-specific capacities and mechanisms, achieved by supplementing behavioral experiments with mechanistic studies."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="milliere-rathkopf-2026-anthropocentric">
    <titleInfo>
        <title>Anthropocentric Bias in Language Model Evaluation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Raphaël</namePart>
        <namePart type="family">Millière</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Charles</namePart>
        <namePart type="family">Rathkopf</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Evaluating the cognitive capacities of large language models (LLMs) requires overcoming not only anthropomorphic but also anthropocentric biases. This article identifies two types of anthropocentric bias that have been neglected: overlooking how auxiliary factors can impede LLM performance despite competence (auxiliary oversight), and dismissing LLM mechanistic strategies that differ from those of humans as not genuinely competent (mechanistic chauvinism). Mitigating these biases requires an empirical, iterative approach to mapping cognitive tasks to LLM-specific capacities and mechanisms, achieved by supplementing behavioral experiments with mechanistic studies.</abstract>
    <identifier type="citekey">milliere-rathkopf-2026-anthropocentric</identifier>
    <identifier type="doi">10.1162/coli.a.582</identifier>
    <location>
        <url>https://aclanthology.org/2026.cl-1.11/</url>
    </location>
    <part>
        <date>2026-03</date>
        <detail type="volume"><number>52</number></detail>
        <detail type="issue"><number>1</number></detail>
        <extent unit="page">
            <start>379</start>
            <end>388</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Journal Article
%T Anthropocentric Bias in Language Model Evaluation
%A Millière, Raphaël
%A Rathkopf, Charles
%J Computational Linguistics
%D 2026
%8 March
%V 52
%N 1
%I MIT Press
%C Cambridge, MA
%F milliere-rathkopf-2026-anthropocentric
%X Evaluating the cognitive capacities of large language models (LLMs) requires overcoming not only anthropomorphic but also anthropocentric biases. This article identifies two types of anthropocentric bias that have been neglected: overlooking how auxiliary factors can impede LLM performance despite competence (auxiliary oversight), and dismissing LLM mechanistic strategies that differ from those of humans as not genuinely competent (mechanistic chauvinism). Mitigating these biases requires an empirical, iterative approach to mapping cognitive tasks to LLM-specific capacities and mechanisms, achieved by supplementing behavioral experiments with mechanistic studies.
%R 10.1162/coli.a.582
%U https://aclanthology.org/2026.cl-1.11/
%U https://doi.org/10.1162/coli.a.582
%P 379-388

Download as File

Markdown (Informal)

[Anthropocentric Bias in Language Model Evaluation](https://aclanthology.org/2026.cl-1.11/) (Millière & Rathkopf, CL 2026)

Anthropocentric Bias in Language Model Evaluation (Millière & Rathkopf, CL 2026)

ACL

Raphaël Millière and Charles Rathkopf. 2026. Anthropocentric Bias in Language Model Evaluation. Computational Linguistics, 52(1):379–388.